Skip to content

✨ Fake news classification using source adaptive framework - BE Project πŸŽ“The repository contains Detailed Documentation of the project, Classification pipeline, Architecture, System Interface Design, Tech stack used.

License

Notifications You must be signed in to change notification settings

hritik5102/Fake-news-classification-model

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

Fake-news-classification-model Β 

Gitpod ready-to-code
contributions welcomeΒ  DonateΒ 

All Contributors

Table of Contents

Introduction

(Back to Top)

Fake news is playing an increasingly dominant role in spreading misinformation by influencing people’s perceptions or knowledge to distort their awareness and decision-making.

The growth of social media and online forums has spurred the spread of fake news causing it to easily blend with truthful information.

This study provides a novel text analytics–driven approach to fake news detection for reducing the risks posed by fake news consumption.

News Cateogries

(Back to Top)

No. Content Discription
1 Fake news Fake News - Sources that entirely fabricate information, disseminate deceptive content, or grossly distort actual news reports,aim of damaging the reputation of a person or entity, or making money through advertising revenue
2 Satire Satire - Sources that use humor, irony, exaggeration, ridicule, and false information to comment on current events, providing fake insights about an on-going real news event.
3 Bias Extreme Bias - Sources that come from a particular point of view and may rely on propaganda, decontextualized information, and opinions distorted as facts.
4 Conspiracy Theories Conspiracy Theory - is an explanation or interpretation of events that is based on questionable or nonexistent evidence, which are almost always completely fabricated, even if individual elements of the theories contain nuggets of fact -- can be presented as fake news when they are packaged as factual news stories.
5 Rumor Rumor - Sources that traffic in rumors, gossip, innuendo, and unverified claims, statement consisting of unverified pieces of information at the time of posting
6 State State News - Sources in repressive states operating under government sanction.
7 Junk science Junk Science - Sources that promote pseudoscience, metaphysics, naturalistic fallacies, and other scientifically dubious claims.
8 Hate Hate News - Sources that actively promote racism (based on something such as religion, ethnicity, nationality, sexual orientation), misogyny, homophobia, and other forms of discrimination.
9 Clickbait Clickbait - Sources that provide generally credible content, but use exaggerated, misleading, or questionable headlines, social media descriptions, and/or images.
10 Unreliable Unreliable - Proceed With Caution, Sources that may be reliable but whose contents require further verification.
11 Political Political - Sources that provide generally verifiable information in support of certain points of view or political orientations.
12 Reliable Credible - Sources that circulate news and information in a manner consistent with traditional and ethical practices in journalism (Remember: even credible sources sometimes rely on clickbait-style headlines or occasionally make mistakes. No news organization is perfect, which is why a healthy news diet consists of multiple sources of information).
13 Celebrity Celebrity - Celebrity/Gossip magazines (sometimes referred to as tabloid magazines) are magazines that feature scandalous stories about the personal lives of celebrities and other well-known individuals.
14 Hoax Hoax - is a news containing facts that are either inaccurate or false but which are presented as genuine. A hoax news conveys a half-truth used deliberately to mislead the public.
15 Unknown Unknown - is a sources that have not yet been analyzed (many of these were suggested by readers/users or are found on other lists and resources). Help us expand our resource by providing us information!
16 Propaganda Propaganda - is the spreading of rumors, information which is often inaccurate and especially of a biased or misleading nature, used to promote a political cause or point of view.
18 Misinformation Misinformation - is false, inaccurate, or misleading information that is communicated regardless of an intention to deceive. Examples of misinformation are false rumors, insults, and pranks.
19 Poor Sourcing Poor Sourcing - is the out-of-context information that does not on its own constitute fake news. This kind of information is not wholly fabricated, and it can exist within a news report that is based on actual events that occurred but does not have the proper evidence for it.
20 Lack of Transparency Lack of Transparency - is the out-of-context information that does not on its own constitute fake news. This kind of information is not wholly fabricated, and it can exist within a news report that is based on actual events that occurred but does not have the proper evidence for it.
21 False Information False Information - Sources that entirely fabricate information, disseminate deceptive content, or grossly distort actual news reports,aim of damaging the reputation of a person or entity, or making money through advertising revenue
22 Sensationalism Sensationalism - In journalism (and more specifically, the mass media), sensationalism is a type of editorial tactic. Events and topics in news stories are selected and worded to excite the greatest number of readers and viewers.
23 Plagarism Plagiarism is the representation of another author's language, thoughts, ideas, or expressions as one's own original work. Plagiarism is considered a violation of integrity and a breach of journalistic ethics.

Architecture

(Back to Top)

Architecture

System interface design

(Back to Top)

Architecture

Poster

(Back to Top)

Poster-01

Poster-02


PDF


PDF

Demo-video

(Back to Top)

Tech stack

(Back to Top)

  1. Programming Language : Python
  2. Frontend : Streamlit
  3. API : VirusTotal API
  4. Platform : Colab notebook, Jupyter notebook, Visual studio code
  5. Testing tool : Apache Jmeter, Google PageSpeed insights, Selenium
  6. Machine learning Library : Tensorflow, PyTorch, Keras, Huggingface transformers, simpletransformers
  7. Web framework : Flask
  8. WSGI server : Gunicorn
  9. Web server : Nginx
  10. Cloud infrastructure support: AWS EC2 instance, AWS secret manager
  11. Containerization/deployment: Docker

Project Deliverables

(Back to Top)

The Project Deliverables includes detailed documentation of the project, including Software Requirement Specifications (SRS), Software Project Management Plan (SPMP), Software Design Description (SDD), Software Testing Document (STD), Implementation details, and Result and conclusion.

Installation

(Back to Top)

Clone git repository

    $ git clone "https://github.com/hritik5102/Fake-news-classification-model"

Prerequisites

(Back to Top)

Run the setup file on git bash or any linux terminal:

$ bash setup.sh

How to run the app?

Run the following commands:

  1. bash start-server.sh on git bash or any linux terminal This will start the deep learning model servers.

  2. cd src

  3. streamlit run app.py

How to stop the Deep learning model servers?

run bash stop-server.sh on git bash or any linux terminal

Google colab notebook

(Back to Top)

Filename Notebook
GPT2 Model Open In Colab
BiLSTM + GloVe Model Open In Colab
BERT Model Open In Colab
Roberta Model Open In Colab

Acknowledgement

(Back to Top)

Some resources have been used to build this project, so I'd like to acknowledge the resources in the reference section. Take a look.

If you think that I've referred any piece of code or material but have not acknowledged it. Please create an issue mentioning the site info & a link pointing to that material.

Support me

(Back to Top)

Buy Me A Coffee

Roadmap

(Back to Top)

See the open issues for a list of proposed features (and known issues).

Contributing

(Back to Top)

Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.

Make sure your changes don't break existing functionality without good reason.

  1. Fork the Project
  2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
  3. Commit your Changes (git commit -m 'Add some AmazingFeature')
  4. Push to the Branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

Discuss the features, ideas you want to add to the project from here πŸ“Œ

License

(Back to Top)

Distributed under the MIT License. See LICENSE for more information.

Contact

(Back to Top)

No. Name Twitter handle 🐦 Email πŸ“©
1. Heet sakaria @HeetSakaria [email protected]
2. Hritik Jaiswal @imhritik_dj [email protected]

Project Link - hritik5102/Fake-news-classification-model (github.com)

Contributors

(Back to Top)

Thanks goes to these wonderful people πŸ‘πŸ‘


Heet Sakaria

πŸ’» πŸ€”πŸ“–πŸ–‹

vedangparasnis

πŸ’»πŸ“–

Viraj Thakkar

πŸ“–
 _____ _                 _     __   __            
|_   _| |               | |    \ \ / /            
  | | | |__   __ _ _ __ | | __  \ V /___  _   _   
  | | | '_ \ / _` | '_ \| |/ /   \ // _ \| | | |  
  | | | | | | (_| | | | |   <    | | (_) | |_| |  
  \_/ |_| |_|\__,_|_| |_|_|\_\   \_/\___/ \__,_| 

(Back to Top)

About

✨ Fake news classification using source adaptive framework - BE Project πŸŽ“The repository contains Detailed Documentation of the project, Classification pipeline, Architecture, System Interface Design, Tech stack used.

Topics

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages